activity
20232025
most citedFrom Canopy to Ground via ForestGen3D: Learning Cross-Domain Generation of 3D Forest Structure from Aerial-to-Terrestrial LiDAR

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2023

Representation Disentaglement via Regularization by Causal Identification

Juan Castorena

In this work, we propose the use of a causal collider structured model to describe the underlying data generative process assumptions in disentangled representation learning. This…